© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49513
    Prev
    Next
    INDEX
    Explanations

    fiscal and revenue matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įéĢļ
    -0.10
    ECH
    -0.10
    躬
    -0.10
    礼æĭľ
    -0.10
    çĽijäºĭä¼ļ
    -0.09
    åĵģç§į
    -0.09
    ıè¿°
    -0.09
    æ²¼
    -0.09
    åįĹéĿŀ
    -0.09
    åľºåľ°
    -0.09
    POSITIVE LOGITS
    è´¢æĶ¿
    0.18
     revenue
    0.15
     fiscal
    0.14
    Revenue
    0.13
     revenues
    0.12
     Revenue
    0.12
    ç¨İæĶ¶
    0.12
     Fiscal
    0.10
    è´¢ç¨İ
    0.10
    æĶ¶åħ¥
    0.10
    Activations Density 0.209%

    No Known Activations